Zobrazeno 1 - 10
of 6 570
pro vyhledávání: '"A. Soufiane"'
A machine learning-based methodology for blending data-driven turbulent closures for the Reynolds-Averaged Navier-Stokes (RANS) equations is proposed to improve the generalizability across different flow scenarios. Data-driven models based on sparse
Externí odkaz:
http://arxiv.org/abs/2410.14431
Autor:
Firdoussi, Aymane El, Seddik, Mohamed El Amine, Hayou, Soufiane, Alami, Reda, Alzubaidi, Ahmed, Hacid, Hakim
Synthetic data has gained attention for training large language models, but poor-quality data can harm performance (see, e.g., Shumailov et al. (2023); Seddik et al. (2024)). A potential solution is data pruning, which retains only high-quality data
Externí odkaz:
http://arxiv.org/abs/2410.08942
Deep neural networks (DNNs) exhibit a remarkable ability to automatically learn data representations, finding appropriate features without human input. Here we present a method for analysing feature learning by decomposing DNNs into 1) a forward feat
Externí odkaz:
http://arxiv.org/abs/2410.04264
Autor:
Belharbi, Soufiane, Pedersoli, Marco, Koerich, Alessandro Lameiras, Bacon, Simon, Granger, Eric
Although state-of-the-art classifiers for facial expression recognition (FER) can achieve a high level of accuracy, they lack interpretability, an important feature for end-users. Experts typically associate spatial action units (AUs) from a codebook
Externí odkaz:
http://arxiv.org/abs/2410.01848
Autor:
Richet, Nicolas, Belharbi, Soufiane, Aslam, Haseeb, Schadt, Meike Emilie, González-González, Manuela, Cortal, Gustave, Koerich, Alessandro Lameiras, Pedersoli, Marco, Finkel, Alain, Bacon, Simon, Granger, Eric
Systems for multimodal emotion recognition (ER) are commonly trained to extract features from different modalities (e.g., visual, audio, and textual) that are combined to predict individual basic emotions. However, compound emotions often occur in re
Externí odkaz:
http://arxiv.org/abs/2407.12927
Autor:
Gross, Jason, Agrawal, Rajashree, Kwa, Thomas, Ong, Euan, Yip, Chun Hei, Gibson, Alex, Noubir, Soufiane, Chan, Lawrence
We propose using mechanistic interpretability -- techniques for reverse engineering model weights into human-interpretable algorithms -- to derive and compactly prove formal guarantees on model performance. We prototype this approach by formally prov
Externí odkaz:
http://arxiv.org/abs/2406.11779
Autor:
Belharbi, Soufiane, Whitford, Mara KM, Hoang, Phuong, Murtaza, Shakeeb, McCaffrey, Luke, Granger, Eric
Confocal fluorescence microscopy is one of the most accessible and widely used imaging techniques for the study of biological processes at the cellular and subcellular levels. Scanning confocal microscopy allows the capture of high-quality images fro
Externí odkaz:
http://arxiv.org/abs/2406.09168
In this paper, we study the role of initialization in Low Rank Adaptation (LoRA) as originally introduced in Hu et al. (2021). Essentially, to start from the pretrained model as initialization for finetuning, one can either initialize B to zero and A
Externí odkaz:
http://arxiv.org/abs/2406.08447
This study presents a new computational approach for simulating the microbial decomposition of organic matter, from 3D micro-computed tomography (micro-CT) images of soil. The method employs a valuated graph of connected voxels to simulate transforma
Externí odkaz:
http://arxiv.org/abs/2406.04177
Autor:
Müller, Niklas, Kabil, Soufiane el, Vosse, Gerrit, Hansen, Lina, Rathje, Christopher, Schäfer, Sascha
Recent advancements in electron microscopy have introduced innovative techniques enabling the inelastic interaction of fast electrons with tightly confined and intense light fields. These techniques, commonly summarized under the term photon-induced
Externí odkaz:
http://arxiv.org/abs/2405.12017